© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48398
    Prev
    Next
    INDEX
    Explanations

    binary `0` or `1` state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç®Ĺä»Ģä¹Ī
    -0.07
    æľĢä¸ĵä¸ļçļĦ
    -0.07
    çĤ¹èĩ³
    -0.06
    为å¸Ī
    -0.06
    è½¬çľ¼
    -0.06
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.06
    æĺ¯ä¸Ģ次
    -0.06
    ÙĬار
    -0.06
    å¾ĢéĩĮ
    -0.06
    æĺ¯ä¸Ģ个人
    -0.06
    POSITIVE LOGITS
     togg
    0.09
    ãģ©ãģ¡ãĤī
    0.09
    è¿Ļ两ç§į
    0.09
    两ç§į
    0.08
     toggle
    0.08
     preference
    0.08
    _Default
    0.08
    Preference
    0.08
     Preference
    0.07
    æŁ´
    0.07
    Activations Density 0.044%

    No Known Activations